[Linkpost] Prefixing names with 'secure_' makes agents write more secure code

·LessWrong··

The graphs are interactive and don't translate well to inline, so the full writeup with figures is in the link.We gave coding agents a three-step synthesis task: build a document management API, then extend it twice. Across conditions we varied the prefix attached to the four initial function names (secure_, safe_, energetic_, lazy_, unsafe_, control). The downstream steps were identical, prefix-neutral prompts. Each task was handed to a fresh agent, with only the codebase as context to influenc...

Read full article →

Related Articles

Anthropic S-1
SiNTEx · Hacker News · 18h ago
Solar power is becoming bigger than nuclear
geox · Hacker News · 16h ago
The Exponential Time Hypothesis Is False [pdf]
vok · Hacker News · 9h ago
Oldest GUI application that still runs on Windows 11
enlyth · Hacker News · 13h ago
Type Server Protocol
adamnemecek · Hacker News · 13h ago